© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36284
    Prev
    Next
    INDEX
    Explanations

    specific numbers or counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /or
    -0.09
    ç¨Ķ
    -0.09
    emb
    -0.09
     пеÑĢвой
    -0.09
    Licensed
    -0.09
    æŁIJç§įç¨ĭ度
    -0.09
    oret
    -0.08
    lean
    -0.08
    æĻ®æĥł
    -0.08
    稳
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.12
    ìĶ©
    0.11
    /all
    0.11
    个å¤ļ
    0.10
    äººåľ¨
    0.10
    ëĿ¼ëıĦ
    0.10
    å°±å¤ŁäºĨ
    0.09
     baÅŁÄ±na
    0.09
    -stop
    0.09
    iros
    0.09
    Activations Density 0.112%

    No Known Activations